Abstract

Action windows—spatiotemporal regions enabling the player’s safe execution of key in-game actions—are foundational to game task planning, yet their automated generation remains underexplored. In stealth games, level designers carefully create guard patrols and environment layouts. However, critical tasks such as planning assassination routes for high-value targets (VIPs) still depend heavily on manual tuning. We formalize VIP task planning as the problem of automatically generating a path through a predefined environment with guard patrols, such that the path contains the player’s safe action windows that are temporally and spatially dispersed, while maintaining coherence and meaningful interactions with environmental elements. We introduce two approaches:

  1. An evolutionary optimization method that efficiently generates diverse routes by balancing multiple objectives.
  2. A constraint-driven safeblock search that guarantees optimal sequences under strict design thresholds.

Initial experiments validate that the evolutionary method produces high-dispersion routes with rapid runtimes, whereas the safeblock approach enforces hard constraints with predictable performance. Both methods integrate directly with existing level and patrol data, offering scalable solutions for automated stealth mission generation.

Citation

Xu, K., & Verbrugge, C. (2025, August). Action Window Planning for Stealth Missions. In 2025 IEEE Conference on Games (CoG) (pp. 1-4). IEEE.

@inproceedings{xu2025actionwindow,
  author    = {Kaijie Xu and Clark Verbrugge},
  title     = {Action Window Planning for Stealth Missions},
  booktitle = {2025 IEEE Conference on Games (CoG)},
  pages     = {1-4},
  year      = {2025},
  month     = {Aug},
  organization={IEEE}
}